User emotion recognition and psychological analysis method based on semantic psychological health model
Through the user emotion recognition and psychological analysis method based on semantic mental health model, the problems of inconsistent options and insufficient fine-grainedness in user psychological analysis are solved, and the careful evaluation and personalized tutoring of adolescent psychological state are achieved.
Patent Information
- Application Number
- CN202411426393.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing user psychological analysis methods have the problem that the user fills in the options and the real options are inconsistent, and the evaluation structure is insufficient in fine-grained, which cannot accurately reflect the user's psychological state, especially in psychological counseling for adolescents.
Using the user emotion recognition and psychological analysis method based on the semantic mental health model, the types of psychological characteristics of the scene to be interacted with are obtained, scene interaction events are determined, student interaction data is triggered, and the pre-trained semantic mental health model is used to perform semantic analysis to calculate the types of psychological characteristics. Probability, generate a Big Five personality record table, dynamically adjust scene interactive events to obtain complete psychological characteristics.
A more objective and detailed evaluation of user psychological status is achieved, which can effectively reflect the user's real psychological status, especially providing personalized help in teenager psychological counseling.
Smart Images

Figure CN118965176A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer psychological analysis technology, and in particular to a user emotion recognition and psychological analysis method based on a semantic psychological health model. Background Art
[0002] In the existing user psychology analysis methods, the user psychology is classified based on filling in test questions. The users are asked to fill in a large number of psychological analysis questions, and the psychological state of the users is inferred and classified based on the user's options. On the one hand, the above psychological analysis methods have the problem that the options filled in by the users are inconsistent with the real options in their hearts, which leads to the problem that the real psychology of the users cannot be objectively reflected; on the other hand, the evaluation structure is not fine-grained enough, and the classification of user psychology often involves a few simple types, which leads to the inability to output a personalized evaluation report on the user's psychological state in a detailed manner.
[0003] Especially in psychological counseling for teenagers, teenagers sometimes resist psychological tests and choose options that do not match their true psychology when answering psychological analysis questions, resulting in subsequent psychological analysis output results that are not helpful for psychological counseling.
[0004] Therefore, the premise of psychological counseling is to obtain data that can reflect the user's true psychological state.
[0005] As an emerging research field in psychology, game psychological testing has gradually attracted the attention of psychology practitioners. The further combination of games and machine learning models has great application potential in the era of big data and can greatly expand the means of psychological measurement.
[0006] Teenagers can freely express their true thoughts in games without being restricted by real-life pressures.
[0007] In game-based assessments, the game is the assessment task, and its main purpose is to elicit evidence of the subject's ability. It is necessary to define the presentation method, game task characteristics, difficulty and number of game tasks, feasible strategies for completing game tasks, and the target level of test behavior.
[0008] For example, strategy games involve cognitive abilities, decision-making abilities, and strategic thinking; simulation games are related to problem-solving abilities, self-awareness, and perspective-taking; and role-playing games require the participation of traits such as imagination, cooperation, and planning. When choosing games as measurement tools, the first thing to consider is the degree of match between the target traits and the game functions.
[0009] Psychological assessment needs to be refined through the user's input data in the game to obtain effective data for psychological assessment. However, in order to obtain effective data, current psychology games are difficult to escape the influence of the question evaluation model, that is, the game often asks users questions in psychological test questions; or, extracting from more complex games, too much invalid data makes it difficult to extract effective data.
[0010] In order to obtain effective data for student psychological analysis, this application provides a user emotion recognition and psychological analysis method based on a semantic mental health model. Summary of the invention
[0011] In order to overcome the problems existing in the related art, the present application provides a user emotion recognition and psychological analysis method based on a semantic mental health model, including: S1. Obtain the type of interaction scenario to be interacted with by the currently logged-in student; the type of interaction scenario to be interacted with includes individual interaction scenario, school interaction scenario and family interaction scenario; S2. Determine a scene interaction event according to the type of the scene to be interacted with; S3, triggering student interaction data according to the scene interaction event; S4, performing semantic analysis on the student interaction data through a pre-trained semantic mental health model, and calculating the probability of psychological characteristics in each psychological characteristic type; S5. Determine the scene interaction event to be triggered in the next round according to the student psychological analysis report.
[0012] In one implementation, determining a scene interaction event according to the type of scene to be interacted with specifically includes: The scene interaction events are events that simulate students' daily lives and are triggered in a time sequence.
[0013] In one embodiment, the scene interaction event is triggered by a scene interaction game performed by students on a device.
[0014] In one implementation, triggering student interaction data according to the scene interaction event specifically includes: S301, obtaining the background image, background characters and dialogue text sequence of the scene interaction event; S302: Calling the large language model to initiate a dialogue with the character according to the dialogue text sequence, and storing the text sequence input by the character and the behavior sequence of the character as the student interaction data.
[0015] In one embodiment, the semantic analysis of the student interaction data is performed using a pre-trained semantic mental health model to calculate the psychological characteristic scores in each psychological characteristic type, specifically including: S401, classifying the encoded student interaction data to obtain the student's psychological characteristic type; S402, determining a psychological characteristic probability according to the determined psychological characteristic type of the student interaction data; S403: Generate a Big Five personality record table according to the psychological characteristic probability.
[0016] In one embodiment, the categorizing of the encoded student interaction data to obtain the student's psychological characteristic type specifically includes: performing word type recognition on the input student interaction data and encoding it into ; in, For emotional words text, For the intent word text, The text for the action word.
[0017] In one embodiment, the probability calculation formula of the psychological characteristic type is:
[0018] in, represents the probability score of the student interaction data being in each of the psychological characteristic types, Indicates the psychological characteristics type, represents the student interaction data after the i-th encoding, represents the weight vector, express .
[0019] In one embodiment, the probability calculation formula of the psychological characteristics is:
[0020] in, express Under the conditions that occur, Probability of occurrence; Psychological characteristics The probability of The psychological characteristics type is probability.
[0021] In one embodiment, the scene interaction event is a text interaction game.
[0022] The technical solution provided by this application may have the following beneficial effects: In the embodiment of the present application, student interaction data is obtained through a series of scene interaction events. The semantic psychological health model is used to perform semantic recognition and psychological classification on the student interaction data, determine the student's psychological characteristic type, and further determine the psychological characteristics. In the next round, the scene interaction event to be triggered is selected according to the undetermined psychological characteristic type until all the student's psychological characteristics are determined.
[0023] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.
[0025] Figure 1 A flowchart of a method for user emotion recognition and psychological analysis shown in an embodiment of the present application; Figure 2 Another schematic diagram of the process of the user emotion recognition and psychological analysis method shown in the embodiment of the present application; Figure 3 This is another flow chart of the user emotion recognition and psychological analysis method shown in the embodiment of the present application. DETAILED DESCRIPTION
[0026] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.
[0027] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0028] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0029] In the existing user psychology analysis methods, the user psychology is classified based on filling in test questions. The users are asked to fill in a large number of psychological analysis questions, and the psychological state of the users is inferred and classified based on the user's options. On the one hand, the above psychological analysis methods have the problem that the options filled in by the users are inconsistent with the real options in their hearts, which leads to the problem that the real psychology of the users cannot be objectively reflected; on the other hand, the evaluation structure is not fine-grained enough, and the classification of user psychology often involves a few simple types, which leads to the inability to output a personalized evaluation report on the user's psychological state in a detailed manner.
[0030] Especially in psychological counseling for teenagers, teenagers sometimes resist psychological tests and choose options that do not match their true psychology when answering psychological analysis questions, resulting in subsequent psychological analysis output results that are not helpful for psychological counseling.
[0031] Therefore, the premise of psychological counseling is to obtain data that can reflect the user's true psychological state.
[0032] As an emerging research field in psychology, game psychological testing has gradually attracted the attention of psychology practitioners. The further combination of games and machine learning models has great application potential in the era of big data and can greatly expand the means of psychological measurement.
[0033] Teenagers can freely express their true thoughts in games without being restricted by real-life pressures.
[0034] In game-based assessments, the game is the assessment task, and its main purpose is to elicit evidence of the subject's ability. It is necessary to define the presentation method, game task characteristics, difficulty and number of game tasks, feasible strategies for completing game tasks, and the target level of test behavior.
[0035] For example, strategy games involve cognitive abilities, decision-making abilities, and strategic thinking; simulation games are related to problem-solving abilities, self-awareness, and perspective-taking; and role-playing games require the participation of traits such as imagination, cooperation, and planning. When choosing games as measurement tools, the first thing to consider is the degree of match between the target traits and the game functions.
[0036] Psychological assessment needs to be refined through the user's input data in the game to obtain effective data for psychological assessment. However, in order to obtain effective data, current psychology games are difficult to escape the influence of the question evaluation model, that is, the game often asks users questions in psychological test questions; or, extracting from more complex games, too much invalid data makes it difficult to extract effective data.
[0037] In order to obtain valid data for student psychological analysis, such as Figure 1 As shown, the embodiment of the present application provides a user emotion recognition and psychological analysis method based on a semantic psychological health model, comprising the following steps: S1. Obtain the type of interaction scenario to be performed by the currently logged-in student; Specifically, the types of scenarios to be interacted with include individual interaction scenarios, school interaction scenarios, and family interaction scenarios.
[0038] Exemplarily, personal activities include activities completed by individuals such as completing homework and recreational activities. The school interaction scenarios are classroom activities and after-school activities, which include classes, recess activities, and after-school activities. Family interaction scenarios include daily activities that students take place at home, such as dinner parties, recreational activities, and the like.
[0039] Specifically, the above-mentioned interactive scenes are pre-stored in a computer-readable medium and recorded as: interactive scene type, activity theme, activity individual, and activity dialogue initiation.
[0040] The user emotion recognition and psychological analysis method of the embodiment of the present application is run on the device side, and students are required to register their ID and complete the information before starting.
[0041] S2. Determine a scene interaction event according to the type of the scene to be interacted with; Specifically, the scene interaction event is an event that simulates the daily life of students and is triggered in a time sequence; the scene interaction event is triggered by a scene interaction game played by students on the device; For example, if the current scene type to be interacted is a school interaction scene, then one of the scene interaction events in the pre-stored school interaction scenes is called for interaction.
[0042] S3, triggering student interaction data according to the scene interaction event; the student interaction data includes: student dialogue and student behavior; like Figure 2 As shown, in step S3, it specifically includes: S301, obtaining the background image, background characters and dialogue text sequence of the scene interaction event; S302: Calling the large language model to initiate a dialogue with the character according to the dialogue text sequence, and storing the text sequence input by the character and the behavior sequence of the character as the student interaction data.
[0043] Exemplarily, if the scene interaction event is a classroom activity, the background image is a classroom, the background characters include class members, and the dialogue text sequence may include classroom questions and whispers.
[0044] Exemplarily, if the scene interaction event is a game between classes, the background image is a corridor or a playground, the background characters include game members, and the dialogue text sequence is a dialogue between games.
[0045] like Figure 3 As shown, S4, semantic analysis is performed on the student interaction data through a pre-trained semantic psychological health model to calculate the probability of psychological characteristics in each psychological characteristic type; For example, in a classroom interaction scenario, the virtual teacher character asks a question to the student character: [How to calculate this inequality?] The student character can enter a dialogue in the chat box to answer, and obtain the student interaction data.
[0046] Specifically, the semantic mental health model identifies the word type of the input student interaction data and encodes it into .
[0047] in, For emotional words text, For the intent word text, The text for the action word.
[0048] S401, input the encoded student interaction data into a classifier for classification to obtain the student's psychological characteristic type. The psychological characteristic type includes: extroversion, agreeableness, responsibility, neuroticism and openness.
[0049] It can be understood that the psychological characteristic types are divided according to the Big Five Personality Theory.
[0050] In the embodiment of the present application, the input The probability of each psychological characteristic type is calculated separately using the following formula;
[0051] in, represents the probability score of the student interaction data being in each of the psychological characteristic types, Indicates the psychological characteristics type, represents the student interaction data after the i-th encoding, represents the weight vector, express .
[0052] Further, step S402 is executed to determine the psychological characteristic probability according to the psychological characteristic type with the highest probability.
[0053] Specifically, the psychological characteristic probability calculation formula is:
[0054] in, express Under the conditions that occur, Probability of occurrence; Psychological characteristics The probability of The psychological characteristics type is probability.
[0055] S403: Generate a Big Five personality record table of the student according to the psychological characteristic probability.
[0056] Specifically, the Big Five personality record table is shown in Table 1.
[0057] Table 1
[0058] S5, determining the scene interaction event to be triggered in the next round according to the psychological characteristics; Specifically, the scene interaction event is performed on a device end, which may be a host, a home computer or a mobile device. The scene interaction event may be linked via a web page end or a mini program end.
[0059] Exemplarily, the scene interaction event of the embodiment of the present application is implemented based on a text interactive game, and the text interactive game is developed through an avg production tool.
[0060] In an embodiment of the present application, probability scores are calculated for the psychological characteristics in Table 1, and the next round of scene interaction events are generated based on the missing items in Table 1.
[0061] In the embodiment of the present application, student interaction data is obtained through a series of scene interaction events. The semantic psychological health model is used to perform semantic recognition and psychological classification on the student interaction data, determine the student's psychological characteristic type, and further determine the psychological characteristics. In the next round, the scene interaction event to be triggered is selected according to the undetermined psychological characteristic type until all the student's psychological characteristics are determined.
[0062] Regarding the device in the above embodiment, the specific way in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.
[0063] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the description are not necessarily required for the present application.
[0064] In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs.
[0065] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.
[0066] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.
[0067] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.
[0068] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and the part of the module, the program segment or the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or the flow chart, and the combination of the square boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0069] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A user emotion recognition and psychological analysis method based on a semantic mental health model, characterized in that: include: S1. Obtain the type of interaction scenario to be performed by the currently logged-in student; The types of scenarios to be interacted with include individual interaction scenarios, school interaction scenarios, and family interaction scenarios; S2. Determine a scene interaction event according to the type of the scene to be interacted with; S3, triggering student interaction data according to the scene interaction event; S4, performing semantic analysis on the student interaction data through a pre-trained semantic mental health model, and calculating the probability of psychological characteristics in each psychological characteristic type; S5. Determine the scene interaction event to be triggered in the next round according to the student psychological analysis report.
2. According to the method of user emotion recognition and psychological analysis based on semantic mental health model in claim 1, it is characterized in that: Determining a scene interaction event according to the type of the scene to be interacted with specifically includes: The scene interaction events are events that simulate students' daily lives and are triggered in a time sequence.
3. According to the method of user emotion recognition and psychological analysis based on semantic mental health model in claim 2, it is characterized in that: The scene interaction event is triggered by the scene interaction game performed by the students on the device side.
4. The user emotion recognition and psychological analysis method based on the semantic mental health model according to claim 1 is characterized in that: The student interaction data is triggered according to the scene interaction event, specifically including: S301, obtaining the background image, background characters and dialogue text sequence of the scene interaction event; S302: Calling the large language model to initiate a dialogue with the character according to the dialogue text sequence, and storing the text sequence input by the character and the behavior sequence of the character as the student interaction data.
5. The user emotion recognition and psychological analysis method based on the semantic mental health model according to claim 1 is characterized in that: The semantic analysis of the student interaction data is performed through the pre-trained semantic mental health model to calculate the psychological characteristic scores in each psychological characteristic type, specifically including: S401, classifying the encoded student interaction data to obtain the student's psychological characteristic type; S402, determining a psychological characteristic probability according to the determined psychological characteristic type of the student interaction data; S403: Generate a Big Five personality record table according to the psychological characteristic probability.
6. The user emotion recognition and psychological analysis method based on the semantic psychological health model according to claim 5 is characterized in that: The coded student interaction data is classified to obtain the student's psychological characteristic type, specifically including: The input student interaction data is identified by word type and encoded as ; in, For emotional words text, For the intent word text, The text for the action word.
7. The method for user emotion recognition and psychological analysis based on a semantic psychological health model according to claim 6, characterized in that: The probability calculation formula for the psychological characteristic type is: in, represents the probability score of the student interaction data being in each of the psychological characteristic types, Indicates the psychological characteristics type, represents the student interaction data after the i-th encoding, represents the weight vector, express .
8. The method for user emotion recognition and psychological analysis based on a semantic psychological health model according to claim 7, characterized in that: The probability calculation formula of the psychological characteristics is: in, express Under the conditions that occur, Probability of occurrence; Psychological characteristics The probability of The psychological characteristics type is probability.
9. The method for user emotion recognition and psychological analysis based on a semantic psychological health model according to claim 1, characterized in that: The scene interaction event is a text interaction game.
Citation Information
Cited By
Student psychological health dynamic assessment method and system based on deep learning
CN120753654A
A deep learning-based student mental health dynamic assessment method and system
CN120753654B
